Understanding the spatial pattern and determinants of Airbnb revenue through a spatial regression approach: Perspective from Indonesian cities

Abstract

Airbnb adoption is growing in Indonesian cities, yet little is known about how its spatial dynamics intersect with urban features and tourism economies in cities of the Global South. This study presents a systematic spatial analysis of Airbnb performance in Indonesia, with a focus on Jakarta and Bandung. Using detailed performance data from AirDNA, we employ spatial autocorrelation and spatial regression models, specifically the Spatial Lag Model (SLM) and Spatial Error Model (SEM), to investigate the potential impact of urban amenities on Airbnb revenue. Our findings reveal distinct city-specific dynamics: in Bandung, Airbnb revenue is positively associated with the presence of restaurants and hotels but negatively correlated with concentrated commercial centres such as shopping malls, reflecting the city’s culinary-driven tourism economy. In contrast, in Jakarta, Airbnb revenue is strongly linked to shopping centres and restaurants, while hotels show no significant influence, suggesting Airbnb operates within differentiated market niches. These results underscore the critical role of local context and associated development policies in shaping platform economies, demonstrating that Airbnb’s performance cannot be generalised across cities, even within the same country. By highlighting the association between spatial factors and short-term rental markets in Indonesia, this paper contributes to the broader debate on sustainable tourism and platform urbanism in the Global South.